Does this skill help with visionOS development?

Yes, Axiom Vision includes support and implementation patterns specifically for visionOS 1+ and the broader xOS ecosystem.

Should I use VisionKit or the Vision framework?

The skill includes a decision tree to help you choose: VisionKit is recommended for system-standard UI behaviors, while the Vision framework is better for custom pipelines, HDR, or high-resolution processing.

Can it help me isolate a subject while excluding the hand holding it?

Yes, it provides a specific implementation pattern that combines subject instance masks with hand pose landmarks to create precise exclusion masks.

Does it support real-time text and barcode scanning?

Yes, it provides guidance on implementing DataScannerViewController for live camera experiences and optimizing VNRecognizeTextRequest for performance.

Axiom Vision for Apple Platforms

Name: Axiom Vision for Apple Platforms
Author: CharlesWiltgen

byCharlesWiltgen

•

233

•

Mobile Development

Implements advanced computer vision capabilities including subject segmentation, text recognition, and pose detection for modern Apple xOS applications.

Axiom Vision is a specialized skill for Apple platform developers that streamlines the implementation of complex computer vision tasks using the Vision and VisionKit frameworks. It provides production-ready patterns for subject lifting, hand and body pose tracking, OCR, and document scanning across iOS, macOS, and visionOS. By offering guided decision trees for API selection and code snippets for high-performance background processing, this skill ensures developers avoid common pitfalls like main-thread blocking, coordinate system mismatches, and unnecessary custom model training.

Key Features

01Subject segmentation and instance mask generation for subject lifting

02Advanced CoreImage compositing for subject isolation and background removal

03Hand and body pose detection with 2D/3D landmark tracking

04Live barcode and QR code scanning via DataScannerViewController

05High-accuracy text recognition (OCR) and structured document extraction

06233 GitHub stars

Use Cases

01Creating fitness or gesture-controlled apps using real-time pose tracking

02Building photo editing features that isolate subjects from backgrounds

03Automating data entry by extracting structured info from scanned documents and receipts

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add charleswiltgen/axiom axiom-vision

For use in Claude.ai and ChatGPT

Download Skill